{"id":"https://openalex.org/W4226191785","doi":"https://doi.org/10.1109/asru51503.2021.9688173","title":"Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR","display_name":"Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226191785","doi":"https://doi.org/10.1109/asru51503.2021.9688173"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688173","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027763497","display_name":"Chung\u2010Cheng Chiu","orcid":"https://orcid.org/0000-0001-9729-4778"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chung-Cheng Chiu","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042631153","display_name":"Tom O\u2019Malley","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom O'Malley","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.0644,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.93284083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"312","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907183170318604},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7371082305908203},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6939600706100464},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6756342053413391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6161785125732422},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.5871949791908264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44321396946907043},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43748411536216736},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.43207603693008423},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4235972762107849},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36136212944984436},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23231613636016846},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.09098219871520996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907183170318604},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7371082305908203},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6939600706100464},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6756342053413391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6161785125732422},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.5871949791908264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44321396946907043},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43748411536216736},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43207603693008423},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4235972762107849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36136212944984436},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23231613636016846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.09098219871520996},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688173","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1992475611","https://openalex.org/W2042141988","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2133564696","https://openalex.org/W2141411743","https://openalex.org/W2473329891","https://openalex.org/W2559809918","https://openalex.org/W2606722458","https://openalex.org/W2617258110","https://openalex.org/W2627092829","https://openalex.org/W2734498959","https://openalex.org/W2739427748","https://openalex.org/W2748545504","https://openalex.org/W2750499125","https://openalex.org/W2760103357","https://openalex.org/W2884797218","https://openalex.org/W2889013998","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2937769560","https://openalex.org/W2953384591","https://openalex.org/W2962935966","https://openalex.org/W2963122170","https://openalex.org/W2964110616","https://openalex.org/W2972818416","https://openalex.org/W2973062255","https://openalex.org/W2981857663","https://openalex.org/W3007328579","https://openalex.org/W3015194534","https://openalex.org/W3016176723","https://openalex.org/W3095095816","https://openalex.org/W3095994005","https://openalex.org/W3096090308","https://openalex.org/W3097777922","https://openalex.org/W3160766462","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3175785186","https://openalex.org/W4210409334","https://openalex.org/W4226428303","https://openalex.org/W4288088457","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6664675605","https://openalex.org/W6665938000","https://openalex.org/W6679434410","https://openalex.org/W6680858114","https://openalex.org/W6713134421","https://openalex.org/W6738243166","https://openalex.org/W6739366949","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6760633627","https://openalex.org/W6761305474","https://openalex.org/W6761675817","https://openalex.org/W6769806307","https://openalex.org/W6775605244","https://openalex.org/W6776402102","https://openalex.org/W6777337586","https://openalex.org/W6781924587","https://openalex.org/W6782496650","https://openalex.org/W6792124657","https://openalex.org/W6797738036"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W4385077663","https://openalex.org/W2052399476","https://openalex.org/W2077273959","https://openalex.org/W2810163160","https://openalex.org/W4220905048","https://openalex.org/W2037964119","https://openalex.org/W1494829770"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"cross-attention":[3,39,66,104],"conformer,":[4],"an":[5,91],"attention-based":[6],"architecture":[7],"for":[8,107],"context":[9,17],"modeling":[10],"in":[11],"speech":[12,99,113],"enhancement.":[13],"Given":[14],"that":[15,30,56],"the":[16,28,51,64],"information":[18,45],"can":[19,68,93],"often":[20],"be":[21,33,69,94],"sequential,":[22],"and":[23,42],"of":[24,38,111],"different":[25],"length":[26],"as":[27,61],"audio":[29,88],"is":[31],"to":[32,40,71,96],"enhanced,":[34],"we":[35,80],"make":[36],"use":[37],"summarize":[41],"merge":[43],"contextual":[44,74],"with":[46],"input":[47],"features.":[48],"Building":[49],"upon":[50],"recently":[52],"proposed":[53,65],"conformer":[54,67,105],"model":[55],"uses":[57],"self":[58],"attention":[59],"layers":[60,106],"building":[62],"blocks,":[63],"used":[70,95],"build":[72,97],"deep":[73],"models.":[75],"As":[76],"a":[77,98],"concrete":[78],"example,":[79],"show":[81],"how":[82],"noise":[83,109],"context,":[84],"i.e.,":[85],"short":[86],"noise-only":[87],"segment":[89],"preceding":[90],"utterance,":[92],"enhancement":[100],"feature":[101],"frontend":[102],"using":[103],"improving":[108],"robustness":[110],"automatic":[112],"recognition.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}